All authors
Claude Skills by VectorSpaceLab
github.com/VectorSpaceLab6,028 skills13 installs7,823 views
- Sr3 Degradation ScheduleBuild paired low/high-resolution items and cumulative diffusion schedules that match SR3 equations. This reusable skill supports bounded SR3 recovery experiments.Votes: 0GitHub stars: 247
- Sr3 Iterative SamplerApply the SR3 reverse-chain update from Gaussian noise to a refined high-resolution image. This reusable skill supports bounded SR3 recovery experiments.Votes: 0GitHub stars: 247
- Sr3 Recovery EvaluationEvaluate SR3-style proxy runs with consistency metrics, source-boundary records, and mechanism checks. This reusable skill supports bounded SR3 recovery experiments.Votes: 0GitHub stars: 247
- Flow Recovery DiagnosticsIntegrate reduced InterFlow velocity fields and summarize executable mechanism-faithful recovery diagnostics.Votes: 0GitHub stars: 247
- Quadratic Velocity ObjectiveCompute and test the simulation-free quadratic velocity objective used by stochastic interpolant flows.Votes: 0GitHub stars: 247
- Stochastic Interpolant ConstructionConstruct endpoint-respecting stochastic interpolant samples and time derivatives for InterFlow recovery experiments.Votes: 0GitHub stars: 247
- Stochastic Interpolant ObjectivesCompute stochastic-interpolant velocity, denoiser, and score objective diagnostics from sampled tuples without evaluating densities.Votes: 0GitHub stars: 247
- Stochastic Interpolant ProtocolConstruct endpoint-valid stochastic interpolant samples with latent schedules and derivative targets for reduced or full generative recovery experiments.Votes: 0GitHub stars: 247
- Stochastic Interpolant RecoveryRun a deterministic reduced Gaussian-mixture recovery that exercises stochastic-interpolant construction, objectives, denoising, and sampling evidence.Votes: 0GitHub stars: 247
- Stochastic Interpolant SamplerIntegrate bounded stochastic-interpolant probability-flow ODE and simple diffusion sampler updates from learned velocity and score fields.Votes: 0GitHub stars: 247
- Bounded Recovery ExperimentRun a bounded CMA-ES proxy experiment that validates sampling, selection, CSA, and covariance adaptation evidence.Votes: 0GitHub stars: 247
- Default Strategy ParametersCompute CMA-ES default strategy parameters from the tutorial formulas for bounded recovery experiments.Votes: 0GitHub stars: 247
- Path Covariance AdaptationUpdate CMA-ES cumulative step-size paths and covariance matrix from selected normalized steps.Votes: 0GitHub stars: 247
- Population Sampling SelectionSample and select CMA-ES Gaussian offspring for derivative-free black-box optimization recovery.Votes: 0GitHub stars: 247
- Imagenet C Corruption MetricsCompute ImageNet-C CE, mCE, relative CE, and relative mCE from clean and corrupted top-1 error tables.Votes: 0GitHub stars: 247
- Imagenet C Corruption ProtocolApply ImageNet-C-style common image corruptions with five severity levels and reproducible metadata for robustness experiments.Votes: 0GitHub stars: 247
- Imagenet C Recovery HarnessRun a bounded mechanism-faithful ImageNet-C proxy recovery using generated corruption and metric skills without reading the original repository.Votes: 0GitHub stars: 247
- Imagenet P Perturbation MetricsCompute ImageNet-P-style prediction flip probability over ordered perturbation sequences.Votes: 0GitHub stars: 247
- Base Ptq Scale SearchUse this skill to calibrate post-training quantization scales for a layer or matrix multiplication using deterministic candidate search.Votes: 0GitHub stars: 247
- Hessian Guided MetricUse this skill to rank quantization candidates with the PTQ4ViT Hessian-guided squared-gradient reconstruction metric.Votes: 0GitHub stars: 247
- Ptq4vit Recovery HarnessUse this skill to run a bounded PTQ4ViT proxy recovery that invokes generated scale-search, twin-quantization, and Hessian-metric skills.Votes: 0GitHub stars: 247
- Twin Uniform QuantizationUse this skill to apply PTQ4ViT twin uniform quantization to post-softmax or post-GELU activations with range flags.Votes: 0GitHub stars: 247
- Sar Collapse RecoveryUse this skill when tracking SAR entropy EMA and deciding whether a model or optimizer reset is required after collapse.Votes: 0GitHub stars: 247
- Sar Norm Adaptation PolicyUse this skill when selecting trainable parameters for SAR-style test-time adaptation while freezing non-normalization model weights.Votes: 0GitHub stars: 247
- Sar Reliable Entropy FilterUse this skill when implementing SAR reliable entropy minimization, entropy-margin filtering, or proxy checks for selected samples.Votes: 0GitHub stars: 247
- Sar Sharpness Aware UpdateUse this skill when implementing the SAM-like sharpness-aware two-step update used by SAR recovery experiments.Votes: 0GitHub stars: 247
- Sar Wild Stream ProtocolUse this skill when a recovery or experiment needs to construct SAR-style dynamic wild-world test streams with mixed domains, small batches, and label imbalance.Votes: 0GitHub stars: 247
- Entropy Adaptation StepRun and validate Tent-style entropy minimization updates on unlabeled target batches with trainable modulation parameters.Votes: 0GitHub stars: 247
- Normalization ConfigurationConfigure normalization layers for Tent by exposing only affine modulation parameters and target batch statistics.Votes: 0GitHub stars: 247
- Recovery EvaluationEvaluate Tent recovery artifacts for numeric metrics, source-boundary compliance, and mechanism-faithful proxy evidence.Votes: 0GitHub stars: 247
- Test Time ProtocolValidate fully test-time adaptation experiments so unlabeled target inputs are the only data used for adaptation updates.Votes: 0GitHub stars: 247
- Vpt Evaluation ProtocolSelect and report Visual Prompt Tuning classification results with validation accuracy and parameter efficiency.Votes: 0GitHub stars: 247
- Vpt Frozen Prompt TrainingConfigure and verify Visual Prompt Tuning trainability with frozen backbone and trainable prompt/head parameters.Votes: 0GitHub stars: 247
- Vpt Mechanism Faithful RecoveryRun a bounded soft-mode Visual Prompt Tuning proxy that proves prompt insertion, frozen training, and evaluation mechanisms.Votes: 0GitHub stars: 247
- Vpt Prompt Token InsertionBuild shallow and deep Visual Prompt Tuning token sequences for Transformer-style image embeddings.Votes: 0GitHub stars: 247
- Cross Task Split ProtocolCreate task-level seen and unseen splits with leakage diagnostics for Natural Instructions style generalization experiments.Votes: 0GitHub stars: 247
- Instruction Encoding VariantsRender Natural Instructions task records into paper-faithful instruction encoding variants for text-to-text models.Votes: 0GitHub stars: 247
- Instruction Schema EncodingEncode Natural-Instructions-style task instructions and inputs into leakage-safe model prompts for cross-task generalization recovery.Votes: 0GitHub stars: 247
- Natural Instruction SchemaNormalize crowdsourcing task instructions into validated Natural Instructions records for cross-task generalization experiments.Votes: 0GitHub stars: 247
- Reduced Bart0 Recovery HarnessRun a bounded soft-mode proxy recovery harness for BART0 cross-task generalization using generated skills and validator-compatible logs.Votes: 0GitHub stars: 247
- Reduced Instruction Training EvaluationExecute a bounded instruction-conditioned training proxy and ROUGE-L evaluation for BART0-style recovery.Votes: 0GitHub stars: 247
- Rouge L EvaluationCompute deterministic ROUGE-L style generation metrics for Natural Instructions recovery outputs and ablations.Votes: 0GitHub stars: 247
- Alpha Subset ProtocolGenerate and validate fixed-cardinality alpha-subset membership matrices for datamodel training and recovery experiments.Votes: 0GitHub stars: 247
- Counterfactual Effect ScoringEstimate training-data removal effects by summing linear datamodel weights and evaluating counterfactual correlations.Votes: 0GitHub stars: 247
- Datamodel Recovery EvaluationRun a bounded synthetic proxy recovery that validates linear datamodel prediction and counterfactual mechanisms with executable evidence.Votes: 0GitHub stars: 247
- Linear Datamodel FitFit target-specific linear datamodel surrogates from subset membership vectors to observed target outcomes.Votes: 0GitHub stars: 247
- Continual Recovery EvaluatorEvaluate mechanism-faithful continual-learning recovery metrics and gate proxy evidence.Votes: 0GitHub stars: 247
- Episodic Memory StoreMaintain frozen-key episodic memory with random write, random replay sampling, and Euclidean KNN retrieval.Votes: 0GitHub stars: 247
- Lifelong Stream ProtocolBuild one-pass lifelong language-learning streams without exposing dataset identifiers to the model.Votes: 0GitHub stars: 247
- Local Adaptation PredictorRetrieve memory neighbors and adapt temporary parameters for a single prediction while preserving base parameters.Votes: 0GitHub stars: 247